© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1146
    Prev
    Next
    INDEX
    Explanations

    [危险] => [危险]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    安全
    -20.50
     safety
    -20.25
     Safety
    -17.63
     Babylon
    -16.75
    的安全
    -16.13
    簋
    -15.75
     safely
    -15.75
    安全性
    -15.69
    文化艺术
    -15.63
    大唐
    -15.25
    POSITIVE LOGITS
     log
    20.38
     sockfd
    19.25
    Socket
    17.25
     Log
    17.25
     logfile
    17.13
    _Log
    17.00
    登录
    16.63
    LoginPage
    16.50
    -log
    16.50
    .Login
    16.50
    Activations Density 0.233%

    No Known Activations